Reinforcing materials modelling by encoding the structures of defects in crystalline solids into distortion scores
The presence of defects in crystalline solids affects material properties, the precise knowledge of defect characteristics being highly desirable. Here the authors demonstrate a machine-learning outlier detection method based on distortion score as an effective tool for modelling defects in crystall...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2020
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/9c4d246c54c44202a50b99c9a8ea072c |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | The presence of defects in crystalline solids affects material properties, the precise knowledge of defect characteristics being highly desirable. Here the authors demonstrate a machine-learning outlier detection method based on distortion score as an effective tool for modelling defects in crystalline solids. |
|---|